Hugging Face's logo

hung200504
/
bert-30

Question Answering
Transformers
PyTorch
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
hung200504 commited on
Commit
b19b4f2
•
1 Parent(s): 945e90e

bert-cased

Browse files
Files changed (3) hide show
  1. README.md +45 -45
  2. pytorch_model.bin +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [deepset/bert-base-cased-squad2](https://huggingface.co/deepset/bert-base-cased-squad2) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 10.2808
19
 
20
  ## Model description
21
 
@@ -34,7 +34,7 @@ More information needed
34
  ### Training hyperparameters
35
 
36
  The following hyperparameters were used during training:
37
- - learning_rate: 4e-05
38
  - train_batch_size: 4
39
  - eval_batch_size: 4
40
  - seed: 42
@@ -46,49 +46,49 @@ The following hyperparameters were used during training:
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
- | 10.3001 | 0.02 | 5 | 12.2937 |
50
- | 11.3113 | 0.05 | 10 | 12.1993 |
51
- | 11.9879 | 0.07 | 15 | 12.1069 |
52
- | 10.7429 | 0.09 | 20 | 12.0165 |
53
- | 11.3554 | 0.11 | 25 | 11.9292 |
54
- | 10.2321 | 0.14 | 30 | 11.8443 |
55
- | 11.1008 | 0.16 | 35 | 11.7623 |
56
- | 10.9742 | 0.18 | 40 | 11.6810 |
57
- | 10.7344 | 0.21 | 45 | 11.6019 |
58
- | 10.9955 | 0.23 | 50 | 11.5246 |
59
- | 9.2042 | 0.25 | 55 | 11.4512 |
60
- | 10.2688 | 0.28 | 60 | 11.3810 |
61
- | 9.8818 | 0.3 | 65 | 11.3127 |
62
- | 10.6999 | 0.32 | 70 | 11.2461 |
63
- | 10.7308 | 0.34 | 75 | 11.1818 |
64
- | 9.8682 | 0.37 | 80 | 11.1196 |
65
- | 10.8196 | 0.39 | 85 | 11.0594 |
66
- | 9.593 | 0.41 | 90 | 11.0016 |
67
- | 10.1361 | 0.44 | 95 | 10.9466 |
68
- | 9.8119 | 0.46 | 100 | 10.8934 |
69
- | 10.3661 | 0.48 | 105 | 10.8424 |
70
- | 9.5482 | 0.5 | 110 | 10.7934 |
71
- | 9.7784 | 0.53 | 115 | 10.7476 |
72
- | 9.9489 | 0.55 | 120 | 10.7027 |
73
- | 9.2101 | 0.57 | 125 | 10.6609 |
74
- | 9.1377 | 0.6 | 130 | 10.6216 |
75
- | 9.4856 | 0.62 | 135 | 10.5843 |
76
- | 9.323 | 0.64 | 140 | 10.5497 |
77
- | 9.583 | 0.67 | 145 | 10.5167 |
78
- | 10.0577 | 0.69 | 150 | 10.4856 |
79
- | 9.4803 | 0.71 | 155 | 10.4569 |
80
- | 9.6417 | 0.73 | 160 | 10.4304 |
81
- | 9.0708 | 0.76 | 165 | 10.4061 |
82
- | 9.6586 | 0.78 | 170 | 10.3842 |
83
- | 9.1787 | 0.8 | 175 | 10.3638 |
84
- | 8.6618 | 0.83 | 180 | 10.3460 |
85
- | 10.0594 | 0.85 | 185 | 10.3302 |
86
- | 8.4156 | 0.87 | 190 | 10.3166 |
87
- | 9.2773 | 0.89 | 195 | 10.3054 |
88
- | 9.0625 | 0.92 | 200 | 10.2959 |
89
- | 9.1544 | 0.94 | 205 | 10.2888 |
90
- | 8.6885 | 0.96 | 210 | 10.2837 |
91
- | 8.6336 | 0.99 | 215 | 10.2808 |
92
 
93
 
94
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [deepset/bert-base-cased-squad2](https://huggingface.co/deepset/bert-base-cased-squad2) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 11.3111
19
 
20
  ## Model description
21
 
 
34
  ### Training hyperparameters
35
 
36
  The following hyperparameters were used during training:
37
+ - learning_rate: 2e-05
38
  - train_batch_size: 4
39
  - eval_batch_size: 4
40
  - seed: 42
 
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
+ | 10.3108 | 0.02 | 5 | 12.3310 |
50
+ | 11.3688 | 0.05 | 10 | 12.2842 |
51
+ | 12.0992 | 0.07 | 15 | 12.2377 |
52
+ | 10.8808 | 0.09 | 20 | 12.1923 |
53
+ | 11.5554 | 0.11 | 25 | 12.1480 |
54
+ | 10.4562 | 0.14 | 30 | 12.1059 |
55
+ | 11.3704 | 0.16 | 35 | 12.0646 |
56
+ | 11.2796 | 0.18 | 40 | 12.0239 |
57
+ | 11.0892 | 0.21 | 45 | 11.9839 |
58
+ | 11.3659 | 0.23 | 50 | 11.9453 |
59
+ | 9.552 | 0.25 | 55 | 11.9083 |
60
+ | 10.7276 | 0.28 | 60 | 11.8726 |
61
+ | 10.3388 | 0.3 | 65 | 11.8381 |
62
+ | 11.2353 | 0.32 | 70 | 11.8045 |
63
+ | 11.3283 | 0.34 | 75 | 11.7717 |
64
+ | 10.4237 | 0.37 | 80 | 11.7398 |
65
+ | 11.4335 | 0.39 | 85 | 11.7099 |
66
+ | 10.1757 | 0.41 | 90 | 11.6803 |
67
+ | 10.8343 | 0.44 | 95 | 11.6522 |
68
+ | 10.4633 | 0.46 | 100 | 11.6252 |
69
+ | 11.1111 | 0.48 | 105 | 11.5994 |
70
+ | 10.2398 | 0.5 | 110 | 11.5743 |
71
+ | 10.5394 | 0.53 | 115 | 11.5506 |
72
+ | 10.7319 | 0.55 | 120 | 11.5279 |
73
+ | 9.9385 | 0.57 | 125 | 11.5065 |
74
+ | 9.8785 | 0.6 | 130 | 11.4861 |
75
+ | 10.2925 | 0.62 | 135 | 11.4670 |
76
+ | 10.1561 | 0.64 | 140 | 11.4492 |
77
+ | 10.4524 | 0.67 | 145 | 11.4327 |
78
+ | 10.9644 | 0.69 | 150 | 11.4166 |
79
+ | 10.3769 | 0.71 | 155 | 11.4020 |
80
+ | 10.5732 | 0.73 | 160 | 11.3882 |
81
+ | 9.9129 | 0.76 | 165 | 11.3757 |
82
+ | 10.593 | 0.78 | 170 | 11.3643 |
83
+ | 10.1119 | 0.8 | 175 | 11.3541 |
84
+ | 9.5165 | 0.83 | 180 | 11.3448 |
85
+ | 11.0571 | 0.85 | 185 | 11.3366 |
86
+ | 9.2427 | 0.87 | 190 | 11.3295 |
87
+ | 10.1903 | 0.89 | 195 | 11.3240 |
88
+ | 9.9867 | 0.92 | 200 | 11.3187 |
89
+ | 10.1191 | 0.94 | 205 | 11.3151 |
90
+ | 9.5425 | 0.96 | 210 | 11.3126 |
91
+ | 9.5164 | 0.99 | 215 | 11.3111 |
92
 
93
 
94
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b43121d05d1b471ed64b9bb143348cebb00a2e8b3c09897c36ffb1039270a728
3
  size 430952617
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9df90d9e5f9e364cbdafc8b7d630b98cc034d49d89690d3370c55b60149b4186
3
  size 430952617
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:43844ba856929d9b1c8d305ffcb14e963a95e3d90a6c0bd2e0a6dc95efb81cd0
3
  size 4027
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01d99687aca72988b22197d0ac0fed531eb54bc435fd76e4d73fbb65bc079d60
3
  size 4027